32 citations · 49 across the 17 of their papers we have counts for
20 papers
Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement Learning
Chiheng Lou, Xiangwei Deng, Bangjun Xiao +4
Agentic reinforcement learning (RL) is commonly used to enhance the capabilities of large language models (LLMs) in solving complex multi-turn tasks. During rollout, agentic RL exh…
Proxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities
Yikai Zhao, Saurabh Pandey, Pradeep Kumar Misra
A deployed LLM agent emits tool calls, queries, and code that can be silently wrong -- by the time the error surfaces, the action has run. Frontier chat APIs hide the model's token…
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Bowen Ye, Lei Li, Shicheng Li +16
Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-source codebases offer a rich source of such tasks, while existi…
A Tri-Agent Framework for Evaluating and Aligning Question Clarification Capabilities of Large Language Models
Yikai Zhao, Saurabh Pandey, Pradeep Kumar Misra
Large Language Models (LLMs) are increasingly deployed in interactive systems where understanding user intent precisely is paramount. A key capability for such systems is effective…
Context-Aware Cluster Decoding: Semantic Anchor-Driven Coherence in dMLLMs
Yikai Zhao, Qiyan Zhao, Jiaquan Zhang +3
Diffusion multimodal large language models (dMLLMs) frequently produce long-form outputs marred by semantic drift and repetition, with quality generally degrading as output length…
TRACE: TRajectory Attribution for Automated Context Engineering
Yikai Zhao, Pradeep Kumar Misra, Saurabh Pandey
Production AI agents fail when their context sources -- system prompts, knowledge bases, tool descriptions, and procedural skills -- contain errors or gaps. Current maintenance rel…
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
TENT: A Declarative Slice Spraying Engine for Performant and Resilient Data Movement in Disaggregated LLM Serving
Feng Ren, Ruoyu Qin, Teng Ma +16
Modern GPU clusters rely on complex, heterogeneous interconnects. As large language model (LLM) serving shifts toward agentic reasoning, KVCache becomes a first-class mobile asset,…
Kimi K2.5: Visual Agentic Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +333
We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that…
Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning
Ruoyu Qin, Weiran He, Weixiao Huang +7
Reinforcement Learning (RL) has emerged as a critical technique for advancing modern Large Language Models (LLMs), yet existing synchronous RL systems face severe performance bottl…
MergeMoE: Efficient Compression of MoE Models via Expert Output Merging
Ruijie Miao, Yilun Yao, Zihan Wang +5
The Mixture-of-Experts (MoE) technique has proven to be a promising solution to efficiently scale the model size, which has been widely applied in recent LLM advancements. However,…
Faithful and Interpretable Explanations for Complex Ensemble Time Series Forecasts using Surrogate Models and Forecastability Analysis
Yikai Zhao, Jiekai Ma
Modern time series forecasting increasingly relies on complex ensemble models generated by AutoML systems like AutoGluon, delivering superior accuracy but with significant costs to…
Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling
Junfeng Ran, Guangxiang Zhao, Yuhan Wu +7
The Mixture-of-Experts (MoE) models have gained significant attention in deep learning due to their dynamic resource allocation and superior performance across diverse tasks. Howev…
Kimi K2: Open Agentic Intelligence
Kimi Team, Yifan Bai, Yiping Bao +195
We introduce Kimi K2, a Mixture-of-Experts (MoE) large language model with 32 billion activated parameters and 1 trillion total parameters. We propose the MuonClip optimizer, which…
Carbonyl4: A Sketch for Set-Increment Mixed Updates
Yikai Zhao, Yuhan Wu, Tong Yang
In the realm of data stream processing, the advent of SET-INCREMENT Mixed (SIM) data streams necessitates algorithms that efficiently handle both SET and INCREMENT operations. We p…
Approaching 100% Confidence in Stream Summary through ReliableSketch
Yuhan Wu, Hanbo Wu, Xilai Liu +6
To approximate sums of values in key-value data streams, sketches are widely used in databases and networking systems. They offer high-confidence approximations for any given key w…
CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models
Hailin Zhang, Zirui Liu, Boxuan Chen +4
Recently, the growing memory demands of embedding tables in Deep Learning Recommendation Models (DLRMs) pose great challenges for model training and deployment. Existing embedding…
ChainedFilter: Combining Membership Filters by Chain Rule
Haoyu Li, Liuhui Wang, Qizhi Chen +5
Membership (membership query / membership testing) is a fundamental problem across databases, networks and security. However, previous research has primarily focused on either appr…
ChameleMon: Shifting Measurement Attention as Network State Changes
Kaicheng Yang, Yuhan Wu, Ruijie Miao +8
Flow-level network measurement is critical to many network applications. Among various measurement tasks, packet loss detection and heavy-hitter detection are two most important me…
QCluster: Clustering Packets for Flow Scheduling
Tong Yang, Jizhou Li, Yikai Zhao +5
Flow scheduling is crucial in data centers, as it directly influences user experience of applications. According to different assumptions and design goals, there are four typical f…